Add alt text generation for media items #78
Merged
+10,157
−9
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Introduced a new TRPC endpoint to generate alt text for media using OpenAI vision. - Added CLI command `media generate-alt` to facilitate alt text generation from the command line. - Implemented a service to handle alt text generation, including image accessibility checks and prompt construction. - Updated media router and CLI command structure to support the new functionality.
…n for images - Added aria-label attributes to video components in MediaGrid, Home, RecordLink, and SearchResultItem for improved accessibility. - Implemented functionality to generate alt text for images during media creation, including error handling for the alt text generation process. - Updated CLI commands and service integrations to support alt text generation, allowing for batch processing of images without descriptions.
…on process - Modified aria-label attributes for video components in MediaGrid, RecordLink, and SearchResultItem to improve accessibility. - Refined alt text generation logic to include dry run options and debug output for better error tracking and processing insights. - Updated CLI commands to support new alt text sync options, allowing for more flexible image processing during media synchronization.
- Added a new timestamp field `altTextGeneratedAt` to the media schema for tracking when alt text is generated. - Improved the alt text generation service by implementing concurrency control and timeout handling for image accessibility checks. - Updated the `callVisionApi` function to support abort signals, allowing for better management of long-running requests. - Refined the `generateAltTextForMedia` function to include the new timestamp field and handle dry runs more effectively. - Introduced progress logging during batch processing of media items to provide better insights into the generation process.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
generateAltTextservice using OpenAI vision API (gpt-5.2) to automatically generate alt text for imagesmedia.generateAltTexttRPC endpoint for batch processingrcr media generate-alt <id...> [--force]CLI commandThe service processes images in batches of 5, validates format/accessibility, uses record context (title, type, URL) in prompts, and invalidates parent record embeddings when alt text changes.
Test plan
rcr media generate-alt <id>on a single image--forceregenerates existing alt text